bcl 0.5.3 → 0.5.4

data/lib/bcl/component_from_spreadsheet.rb

@@ -1,17 +1,17 @@
 ######################################################################
-#  Copyright (c) 2008-2013, Alliance for Sustainable Energy.
+#  Copyright (c) 2008-2014, Alliance for Sustainable Energy.
 #  All rights reserved.
-#  
+#
 #  This library is free software; you can redistribute it and/or
 #  modify it under the terms of the GNU Lesser General Public
 #  License as published by the Free Software Foundation; either
 #  version 2.1 of the License, or (at your option) any later version.
-#  
+#
 #  This library is distributed in the hope that it will be useful,
 #  but WITHOUT ANY WARRANTY; without even the implied warranty of
 #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 #  Lesser General Public License for more details.
-#  
+#
 #  You should have received a copy of the GNU Lesser General Public
 #  License along with this library; if not, write to the Free Software
 #  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
@@ -23,49 +23,46 @@ require 'rubyXL'
 require 'bcl'
 
 module BCL
-
   WorksheetStruct = Struct.new(:name, :components)
   HeaderStruct = Struct.new(:name, :children)
   ComponentStruct = Struct.new(:row, :name, :uid, :version_id, :headers, :values)
 
   class ComponentFromSpreadsheet
-
     @@changed = false
 
     public
 
-    #initialize with Excel spreadsheet to read
-    def initialize(xlsx_path, worksheet_names =["all"])
-
+    # initialize with Excel spreadsheet to read
+    def initialize(xlsx_path, worksheet_names = ['all'])
       @xlsx_path = Pathname.new(xlsx_path).realpath.to_s
       @worksheets = []
 
       begin
-        xlsx= RubyXL::Parser.parse(@xlsx_path)
+        xlsx = RubyXL::Parser.parse(@xlsx_path)
 
-        #by default, operate on all worksheets
-        if worksheet_names == ["all"]
+        # by default, operate on all worksheets
+        if worksheet_names == ['all']
           xlsx.worksheets.each do |xlsx_worksheet|
             parse_xlsx_worksheet(xlsx_worksheet)
           end
-        else #if specific worksheets are specified, operate on them
+        else # if specific worksheets are specified, operate on them
           worksheet_names.each do |worksheet_name|
             parse_xlsx_worksheet(xlsx[worksheet_name])
           end
         end
 
-        #save spreadsheet if changes have been made
+        # save spreadsheet if changes have been made
         if @@changed
           xlsx.write(@xlsx_path)
-          puts "[ComponentFromSpreadsheet] Spreadsheet changes saved"
+          puts '[ComponentFromSpreadsheet] Spreadsheet changes saved'
         end
       ensure
-        xlsx=nil
+        xlsx = nil
       end
     end
 
     def save(save_path, chunk_size = 1000, delete_old_gather = false)
-      #FileUtils.rm_rf(save_path) if File.exists?(save_path) and File.directory?(save_path)
+      # FileUtils.rm_rf(save_path) if File.exists?(save_path) and File.directory?(save_path)
       # TODO: validate against taxonomy
 
       @worksheets.each do |worksheet|
@@ -91,19 +88,19 @@ module BCL
               author = values.delete_at(0)
               datetime = values.delete_at(0)
               if datetime.nil?
-                #puts "[ComponentSpreadsheet] WARNING missing the date in the datetime column in the spreadsheet - assuming today"
+                # puts "[ComponentSpreadsheet] WARNING missing the date in the datetime column in the spreadsheet - assuming today"
                 datetime = DateTime.new
               end
 
               comment = values.delete_at(0)
-              component_xml.add_provenance(author.to_s, datetime.strftime("%Y-%m-%d"), comment.to_s)
+              component_xml.add_provenance(author.to_s, datetime.strftime('%Y-%m-%d'), comment.to_s)
             elsif /tag/i.match(header.name)
               value = values.delete_at(0)
               component_xml.add_tag(value)
             elsif /attribute/i.match(header.name)
               value = values.delete_at(0)
               name = header.children[0]
-              units = ""
+              units = ''
               if match_data = /(.*)\((.*)\)/.match(name)
                 name = match_data[1].strip
                 units = match_data[2].strip
@@ -126,12 +123,12 @@ module BCL
               filename = values.delete_at(0)
               filetype = values.delete_at(0)
               filepath = values.delete_at(0)
-              #not all components(rows) have all files; skip if filename "" or nil
-              next if filename == "" or filename == nil
-              #skip the file if it doesn't exist at the specified location
-              if not File.exists?(filepath)
+              # not all components(rows) have all files; skip if filename "" or nil
+              next if filename == '' or filename.nil?
+              # skip the file if it doesn't exist at the specified location
+              unless File.exist?(filepath)
                 puts "[ComponentFromSpreadsheet] ERROR #{filepath} -> File does not exist, will not be included in component xml"
-                next #go to the next file
+                next # go to the next file
               end
               component_xml.add_file(software_program, version, filepath, filename, filetype)
             else
@@ -150,22 +147,22 @@ module BCL
 
     def parse_xlsx_worksheet(xlsx_worksheet)
       worksheet = WorksheetStruct.new
-      worksheet.name = xlsx_worksheet[0][0].value #get A1, order is: row, col
+      worksheet.name = xlsx_worksheet[0][0].value # get A1, order is: row, col
       worksheet.components = []
       puts "[ComponentFromSpreadsheet] Starting parsing components of type #{worksheet.name}"
 
       # find number of rows, first column should be name, should not be empty
 
       xlsx_data = xlsx_worksheet.extract_data
-      #puts "Data: #{xlsx_data.inspect}"
+      # puts "Data: #{xlsx_data.inspect}"
 
       num_rows = xlsx_data.size
-      #puts "Number of Rows: #{xlsx_data.size}"
+      # puts "Number of Rows: #{xlsx_data.size}"
       num_rows = 2
-      while true do
+      while true
         test = xlsx_data[num_rows][0]
         if test.nil? or test.empty?
-          #num_rows -= 1
+          # num_rows -= 1
           break
         end
         num_rows += 1
@@ -176,12 +173,12 @@ module BCL
       header = nil
       max_col = nil
 
-      xlsx_data[0].each_with_index do |col, index|
+      xlsx_data[0].each_with_index do |_col, index|
         value1 = xlsx_data[0][index]
         value2 = xlsx_data[1][index]
 
         if not value1.nil? and not value1.empty?
-          if not header.nil?
+          unless header.nil?
             headers << header
           end
           header = HeaderStruct.new
@@ -190,7 +187,7 @@ module BCL
         end
 
         if not value2.nil? and not value2.empty?
-          if not header.nil?
+          unless header.nil?
             header.children << value2
           end
         end
@@ -202,18 +199,18 @@ module BCL
         max_col = index
       end
 
-      if not header.nil?
+      unless header.nil?
         headers << header
       end
 
-      if not headers.empty?
-        headers[0].name = "description"
+      unless headers.empty?
+        headers[0].name = 'description'
       end
 
       puts "  Found #{num_rows - 2} components"
 
       components = []
-      for i in 2..num_rows-1 do
+      for i in 2..num_rows - 1 do
         component = ComponentStruct.new
         component.row = i